"Finding the best AI assistant for online searches and tasks" matching MCP servers:

Carbon-aware MCP scheduler that defers "do it later" / "by tomorrow" / "overnight" LLM tasks to the cleanest electricity-grid hour inside a deadline — 40-70% lower CO2 per task, 50% cheaper via Anthropic/OpenAI Batch APIs. 9 MCP tools, per-task carbon receipts to local SQLite, Apache-2.0.

MCP server that enables AI-powered EV charging station management, including live session tracking, automatic battery state detection, remote cable unlock, and RAG-based technical support from OCPP documentation.

Secure typed access to Home Assistant for AI clients like ChatGPT and Codex, with 99 tools for controlling and monitoring devices, automations, energy, and more.

MCP server that provides live facility data access and operational tools, enabling the AI agent to query sensor readings, HVAC status, energy usage, alerts, and execute confirmed maintenance actions.

Enables calculation of the most economical fuel (gasoline, ethanol, or natural gas) based on prices and vehicle consumption, following the 70% rule for ethanol and 60% for GNV.

Exposes EnergyPlus simulation control (run, parse metrics, edit schedules) as LLM tools for autonomous building energy optimization.

Provides real-time South African load shedding data through the EskomSePush API. Enables users to check current load shedding stages, monitor API usage, and access area-specific schedules and searches with natural language queries.

Enables AI agents to choose the lowest-carbon cloud region for a workload, with tools for ranking regions by carbon intensity and latency, and for finding optimal start times to reduce emissions.

Enables monitoring and control of SwitchBot devices (temperature sensors, plugs, bots) via Claude Desktop or Home Assistant.

Provides real-time electricity grid data including CO2 intensity, power mix, and wholesale prices, plus optimal green time windows for energy-intensive AI tasks. Supports UK, Germany, and global regions with optional API keys.

Enables users to query current and historical UK electricity carbon intensity, generation mix, and regional intensity data to schedule energy-intensive tasks during low-carbon periods.

Enables querying historical Home Assistant data from InfluxDB, including energy consumption, entity history, device uptime, and custom InfluxQL queries.

Enables utility operators to forecast transformer oil temperature, assess synthetic outage risk, rank impacted assets, and generate maintenance plans through IBM Bob MCP tools.

Provides tools for querying Danish day-ahead electricity prices, finding cheapest charging windows, estimating costs, and creating pending charging plans, with strict validation and human-in-the-loop approval for write operations.

Nine tools for indoor climate and household energy in Germany/EU: BTU sizing for a room, portable-AC window-seal length, live heatwave outlook, appliance running costs, heating watts, dew point for safe ventilation, and balcony-storage subsidy rules. Also searches and reads 133 guides on getecoback.com; no auth, no personal data, and every answer returns its source URL.

Exposes EnergyPlus building simulation tools as MCP endpoints, enabling LLMs to run closed-loop energy optimization while maintaining occupant comfort.

Hourly electricity grid carbon intensity (gCO2eq/kWh) for 45 zones across Europe, the US and Great Britain, computed from ENTSO-E, EIA and NESO generation data. Four read-only tools; every value carries its interval timestamp and how stale it is. No API key, no account.

An unofficial read-only MCP server for Panasonic AiSEG2 home energy management controllers, enabling clients to read live power flow, per-circuit consumption, circuit names, daily totals, and historical energy/cost data from the device's local web interface.

Unofficial MCP server for the messdienst24.de utility portal, providing tools to retrieve heating and hot-water consumption data, download PDF reports, and compare usage trends.

Read-only MCP server for Home Assistant that computes statistical summaries, trends, and session detection from recorded sensor history, returning compact tables instead of raw data so small local models can answer questions about energy usage, climate, and appliance activity without token-heavy arithmetic.